Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    E

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liver
    -0.07
     secondo
    -0.06
    唇
    -0.06
    FileManager
    -0.06
    oration
    -0.06
    HEMA
    -0.06
    Qi
    -0.06
    iola
    -0.06
    getto
    -0.06
     ><?
    -0.06
    POSITIVE LOGITS
     inland
    0.07
    ACING
    0.07
    .Health
    0.07
    bond
    0.07
     gaining
    0.07
     σας
    0.06
    _Private
    0.06
    STATIC
    0.06
    /st
    0.06
    Listen
    0.06
    Act Density 0.026%

    No Known Activations